Hyperpixel Flow: Semantic Correspondence With Multi-Layer Neural Features

Juhong Min, Jongmin Lee, Jean Ponce, Minsu Cho; The IEEE International Conference on Computer Vision (ICCV), 2019, pp. 3395-3404

Abstract


Establishing visual correspondences under large intra-class variations requires analyzing images at different levels, from features linked to semantics and context to local patterns, while being invariant to instance-specific details. To tackle these challenges, we represent images by "hyperpixels" that leverage a small number of relevant features selected among early to late layers of a convolutional neural network. Taking advantage of the condensed features of hyperpixels, we develop an effective real-time matching algorithm based on Hough geometric voting. The proposed method, hyperpixel flow, sets a new state of the art on three standard benchmarks as well as a new dataset, SPair-71k, which contains a significantly larger number of image pairs than existing datasets, with more accurate and richer annotations for in-depth analysis.

Related Material


[pdf]
[bibtex]
@InProceedings{Min_2019_ICCV,
author = {Min, Juhong and Lee, Jongmin and Ponce, Jean and Cho, Minsu},
title = {Hyperpixel Flow: Semantic Correspondence With Multi-Layer Neural Features},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}